Analysis of Memory System of Tiled Many-Core Processors

Tiled many-core processors are designed to integrate simple cores onto a single chip to take advantage of software-level parallelism, and these cores are interconnected via mesh-based networks to mitigate overheads such as limited throughput derived from traditional interconnects. As these processor...

Full description

Bibliographic Details
Main Authors: Ye Liu, Shinpei Kato, Masato Edahiro
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
UMA
Online Access:https://ieeexplore.ieee.org/document/8628953/
id doaj-bf577c10517640b0b399ba3dcb95b6c5
record_format Article
spelling doaj-bf577c10517640b0b399ba3dcb95b6c52021-03-29T22:19:29ZengIEEEIEEE Access2169-35362019-01-017189641897710.1109/ACCESS.2019.28957018628953Analysis of Memory System of Tiled Many-Core ProcessorsYe Liu0https://orcid.org/0000-0003-0007-722XShinpei Kato1Masato Edahiro2Graduate School of Information Science, Nagoya University, Nagoya, JapanGraduate School of Information Science and Technology, The University of Tokyo, Tokyo, JapanGraduate School of Information Science, Nagoya University, Nagoya, JapanTiled many-core processors are designed to integrate simple cores onto a single chip to take advantage of software-level parallelism, and these cores are interconnected via mesh-based networks to mitigate overheads such as limited throughput derived from traditional interconnects. As these processors become more prevalent, one unnoticed problem is that it is more likely for operating system (OS) designers to believe that these processors, which have multiple on-chip memory controllers, belong to the non-uniform memory access (NUMA) system. In this paper, we define novel models regarding the differentiation between uniform memory access and NUMA on tiled many-core processors from the perspective of the cache system to facilitate OS designers and application programmers in fully understanding the underlying hardware. Whether or not a tiled many-core processor belongs to the NUMA system, is determined by the cache system rather than how many memory controllers it has. The experimental results together with the novel models are able to explain why the (non-)significant performance difference can be observed on KNL and TILE-Gx72.https://ieeexplore.ieee.org/document/8628953/NUMAUMAmemory systemtiled many-core processorss
collection DOAJ
language English
format Article
sources DOAJ
author Ye Liu
Shinpei Kato
Masato Edahiro
spellingShingle Ye Liu
Shinpei Kato
Masato Edahiro
Analysis of Memory System of Tiled Many-Core Processors
IEEE Access
NUMA
UMA
memory system
tiled many-core processorss
author_facet Ye Liu
Shinpei Kato
Masato Edahiro
author_sort Ye Liu
title Analysis of Memory System of Tiled Many-Core Processors
title_short Analysis of Memory System of Tiled Many-Core Processors
title_full Analysis of Memory System of Tiled Many-Core Processors
title_fullStr Analysis of Memory System of Tiled Many-Core Processors
title_full_unstemmed Analysis of Memory System of Tiled Many-Core Processors
title_sort analysis of memory system of tiled many-core processors
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2019-01-01
description Tiled many-core processors are designed to integrate simple cores onto a single chip to take advantage of software-level parallelism, and these cores are interconnected via mesh-based networks to mitigate overheads such as limited throughput derived from traditional interconnects. As these processors become more prevalent, one unnoticed problem is that it is more likely for operating system (OS) designers to believe that these processors, which have multiple on-chip memory controllers, belong to the non-uniform memory access (NUMA) system. In this paper, we define novel models regarding the differentiation between uniform memory access and NUMA on tiled many-core processors from the perspective of the cache system to facilitate OS designers and application programmers in fully understanding the underlying hardware. Whether or not a tiled many-core processor belongs to the NUMA system, is determined by the cache system rather than how many memory controllers it has. The experimental results together with the novel models are able to explain why the (non-)significant performance difference can be observed on KNL and TILE-Gx72.
topic NUMA
UMA
memory system
tiled many-core processorss
url https://ieeexplore.ieee.org/document/8628953/
work_keys_str_mv AT yeliu analysisofmemorysystemoftiledmanycoreprocessors
AT shinpeikato analysisofmemorysystemoftiledmanycoreprocessors
AT masatoedahiro analysisofmemorysystemoftiledmanycoreprocessors
_version_ 1724191893910192128